|
Titel |
An Expert System for Computer-aided Volcano Monitoring on Mt. Etna |
VerfasserIn |
Flavio Cannavò, Andrea Cannata, Carmelo Cassisi, Giuseppe Di Grazia, Placido Montalto, Michele Prestifilippo, Eugenio Privitera, Salvatore Gambino, Mauro Coltelli |
Konferenz |
EGU General Assembly 2017
|
Medientyp |
Artikel
|
Sprache |
en
|
Digitales Dokument |
PDF |
Erschienen |
In: GRA - Volume 19 (2017) |
Datensatznummer |
250143734
|
Publikation (Nr.) |
EGU/EGU2017-7486.pdf |
|
|
|
Zusammenfassung |
Constant estimation of the state of potentially hazardous volcanos plays a crucial role for civil
protection purposes. In particular, the importance of monitoring volcanic activity, especially
for paroxysms that usually come with tephra emissions, is crucial not only for hazards to the
local population but also for airline traffic. Indeed,
At present, real-time surveillance of most volcanoes worldwide is essentially deputized to
one or more human experts in volcanology, who interpret data coming from different kind of
monitoring networks.
Unfavourably, the coupling of highly nonlinear and complex volcanic dynamic processes
leads to measurable effects that can show a large variety of different behaviours. Moreover,
due to intrinsic uncertainties and possible failures in some recorded data, the volcano state
needs to be expressed in probabilistic terms, thus making the fast volcano state assessment
sometimes impracticable for the personnel on duty at the control rooms. With the aim of
aiding the personnel on duty in volcano surveillance, we present an expert system based on a
probabilistic graphical model to estimate automatically the ongoing volcano state from all the
available different kind of measurements. The system consists of a decision network able to
represent a set of variables and their conditional dependencies via a directed acyclic
graph. The model variables are both the measurements and the possible states of
the volcano through the time. The model output is the most likely volcanic state.
We tested the expert system on the Mt. Etna (Italy) case study by considering a
long record of multivariate data from 2011 to 2015 and cross-validated it. Results
indicate that the proposed model is effective and of great power for decision making
purposes. |
|
|
|
|
|